Developing RAG Based Applications

Course Description

In this course, students explore the core architecture and real-world applications of Retrieval-Augmented Generation (RAG)-a powerful way to enhance large language models with access to external knowledge. Through hands-on work with document processing pipelines, chunking strategies, embedding models, and vector databases, students gain practical skills in retrieving and enhancing needed information, augmenting prompts, and evaluating performance with key metrics.

Designed for professionals and teams in companies of all sizes, this course shows how RAG can power tools like internal knowledge assistants, research agents, and customer feedback analyzers. With a focus on agentic RAG, where AI can reason and retrieve dynamically, participants learn to build advanced solutions that drive efficiency, insight, and smarter workflows across the organization. As RAG capabilities become more valuable in the workplace, those who can implement them are increasingly essential to innovation and impact.

Learning Outcomes
At the conclusion of the course, you should be able to

• Explain the architecture and components of Retrieval-Augmented Generation (RAG) systems, including document pipelines, embedding models, and vector databases.
• Apply document retrieval and context augmentation techniques to enhance large language model responses in practical scenarios.
• Analyze the performance of RAG-based applications using evaluation metrics to assess relevance, accuracy, and efficiency.
• Design and develop AI-powered tools such as knowledge assistants or feedback analyzers that leverage agentic RAG for business or research purposes.